How Replication Could Teach Machines What Good Science Looks Like — Edward Hughes

How do we start to build AI scientist systems that go beyond simply answering questions that we pose and start to ask the kinds of questions that lead to open-ended creative discovery?. You spoke about Move 37 and I think you and I would agree that that was definitely creative.

It goes beyond the title with direct discussion of think, it's, which, including: You spoke about Move 37 and I think you and I would agree that that was definitely creative.

1. 01How do we start to build AI scientist systems that go beyond simply answering questions that we pose and start to ask the kinds of questions that lead to open-ended creative discov
2. 02And what we find is that our Faraday agent is able to perform better than the frontier models
3. 03But it's also performing better than other frontier coding agents like Claude, for instance